Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add norman-finance/norman-mcp-server --skill accounting-cutovergit clone --depth 1 https://github.com/norman-finance/norman-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/norman-finance/norman-mcp-server/accounting-cutover)<a href="https://agentmods.dev/skills/norman-finance/norman-mcp-server/accounting-cutover"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/accounting-cutover/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/norman-finance/norman-mcp-server/accounting-cutover"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/accounting-cutover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00982 |
| Opus 5.5 | $0.00020 | $0.00393 |
| Sonnet 5.5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
accounting-cutover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide a company through an accounting migration without changing its Ledger until the user has reviewed the preview and explicitly confirmed the import.
1. Inspect the current setup
- Call
get_accounting_setupfor the relevant fiscal year. - Note the current SKR framework, existing cutover state and any previously imported entries.
- Do not switch SKR03 or SKR04 automatically. A framework switch has broader accounting consequences and requires its own explicit confirmation.
2. Collect and analyze source files
- Upload the available DATEV files or supporting documents and retain their short-lived
file_refvalues. - Call
analyze_accounting_cutover_documentswith all related files together. - Present the detected file roles, fiscal periods, likely SKR framework and any ambiguity to the user.
- Ask for a replacement file when a reference has expired.
File limits enforced by the Accounting API:
- 1 to 20 files per analysis
- 20 MB per file and 100 MB in total
- PDFs may be analyzed as supporting evidence, but opening-balance and booking-stack inputs for Preview and Apply must be machine-readable DATEV or CSV files
3. Choose the migration scenario
formation: a newly formed GmbH or UG with legal opening entriesyear_start: prior-year closing balances become this year's opening balancesmid_year: opening balances plus all bookings through the cutover date
Choose opening_method=datev when an opening-balance file exists. Choose opening_method=manual only when the user wants to enter non-zero account balances directly. Manual rows require account_code, side (debit or credit), amount, and may include memo.
4. Preview before writing
- Call
preview_accounting_cutoverwith the complete set of dates, files and manual rows. - Explain reconciliation totals, detected periods, blockers and warnings in plain language.
- Treat Preview as read-only. It does not write Ledger entries.
- Resolve every blocking finding before proceeding.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 19d ago Changed · +11 lines 1e7f048015f0
- 1mo ago First seen · 61 lines · 50 tokens per session scan A c199c5770a3a
accounting-cutover is a skill published in the GitHub repository norman-finance/norman-mcp-server (61 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 982 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bukio-cli
Drive bukio-cli — agent-first double-entry bookkeeping for SMEs across eleven jurisdictions. Book invoices, archive the originals, keep the books balanced.
QuickBooks Automation
Automate QuickBooks accounting workflows including invoicing, expenses, reporting, and bank reconciliation.
visma-eaccounting
Integration with Visma eAccounting API for bookkeeping and invoicing. Use when the user wants to interact with Visma eAccounting to manage invoices, customers, suppliers, upload receipts/documents, handle accounting operations, or automate bookkeeping tasks. Triggers include mentions of "Visma", "eAccounting"…
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
provider-cost-comparison
Prices your real LangWatch usage mix against other model providers. Exports your actual token mix per model, including the cache read and write split, fetches current price cards, and reprices the same month of usage under each candidate, with the cache sensitivity stated. Use when someone asks whether a cheaper…
paymentsim
Run billing against paymentsim, haven's Stripe stand-in: checkout, subscriptions, invoices, signed webhooks, the test clock, payment failures and exact metered-usage totals. Use when someone says 'haven payment', 'test billing locally', 'fake Stripe', 'stripe webhook locally', 'advance the billing clock', 'fail a…